Systems and methods for vision system tracking in an environment based on detected movements and dwell time

Abstract

Disclosed herein are apparatuses and methods for tracking occupancy count in an environment based on detected movements and dwell time. An implementation may comprise detecting a person in a plurality of image frames captured by a camera. The implementation may comprise tracking a movement of the person and determining that the person has crossed a boundary within the plurality of image frames. The implementation may comprise identifying a path of the person based on the tracked movement and may comprise calculating a dwell time in response to determining that a difference between the identified path and at least one target path associated with entering or exiting the environment exceeds a threshold difference. The implementation may comprise comparing the dwell time to a target dwell time, and updating and storing the occupancy count of the environment in response to determining that the dwell time is less than the target dwell time.

What is claimed is: 
     
         1 . A vision system, comprising:
 a camera;   a memory; and   a processor communicatively coupled with the memory and configured to:
 detect a person in a plurality of image frames captured by the camera, wherein the plurality of image frames depict an access point providing egress and ingress to an environment; 
 track a movement of the person in the plurality of image frames; 
 determine that the person has crossed a boundary within the plurality of image frames; 
 identify a path of the person based on the tracked movement; 
 compare the identified path with at least one target path associated with entering or exiting the environment; 
 calculate a dwell time indicative of an amount of time that the person remains within the plurality of image frames, in response to determining, based on comparing, that a difference between the identified path and the at least one target path exceeds a threshold difference; 
 compare the dwell time to a target dwell time; 
 update an occupancy count of the environment in response to determining that the dwell time is less than the target dwell time; and 
 store, in the memory, an updated value for the occupancy count. 
   
     
     
         2 . The vision system of  claim 1 , wherein the target dwell time is an average dwell time calculated based on historic ingress and egress data associated with the access point, wherein the processor is further configured to:
 update the at least one target path based on the identified path of the person; and   update the target dwell time based on the dwell time of the person.   
     
     
         3 . The vision system of  claim 1 , wherein crossing the boundary is indicative of entering or exiting the environment. 
     
     
         4 . The vision system of  claim 1 , wherein the environment has a plurality of access points, and each access point has at least one target path associated with entering the environment and at least one target path associated with exiting the environment. 
     
     
         5 . The vision system of  claim 4 , wherein the processor is further configured to:
 select the at least one target path to compare with the identified path based on the access point depicted in the plurality of image frames.   
     
     
         6 . The vision system of  claim 1 , wherein the processor is further configured to update the occupancy count of the environment in response to determining that the difference between the identified path and the at least one target path does not exceed the threshold difference. 
     
     
         7 . The vision system of  claim 1 , wherein the processor is further configured to:
 not update the occupancy count of the environment in response to determining that the dwell time is greater than the target dwell time.   
     
     
         8 . The vision system of  claim 1 , wherein the path is a combination of vectors. 
     
     
         9 . The vision system of  claim 1 , wherein the plurality of image frames are received in real-time from the camera as a live video feed. 
     
     
         10 . The vision system of  claim 1 , wherein the processor is further configured to:
 update a user interface on a display to present the updated value of the occupancy count.   
     
     
         11 . The vision system of  claim 1 , wherein the processor is further configured to:
 generate an alert in response to determining that the updated value of the occupancy count is greater than a threshold occupancy count; and   output the alert on a computing device.   
     
     
         12 . A method for tracking by a vision system, comprising:
 detecting a person in a plurality of image frames captured by a camera, wherein the plurality of image frames depict an access point providing egress and ingress to an environment;   tracking a movement of the person in the plurality of image frames;   determining that the person has crossed a boundary within the plurality of image frames;   identifying a path of the person based on the tracked movement;   comparing the identified path with at least one target path associated with entering or exiting the environment;   calculating a dwell time indicative of an amount of time that the person remains within the plurality of image frames, in response to determining that a difference between the identified path and the at least one target path exceeds a threshold difference;   comparing the dwell time to a target dwell time;   updating an occupancy count of the environment in response to determining that the dwell time is less than the target dwell time; and   storing, in a memory, an updated value for the occupancy count.   
     
     
         13 . The method of  claim 12 , wherein the target dwell time is an average dwell time calculated based on historic ingress and egress data associated with the access point, further comprising:
 updating the at least one target path based on the identified path of the person; and   updating the target dwell time based on the dwell time of the person.   
     
     
         14 . The method of  claim 12 , wherein crossing the boundary is indicative of entering or exiting the environment. 
     
     
         15 . The method of  claim 12 , wherein the environment has a plurality of access points, and each access point has at least one target path associated with entering the environment and at least one target path associated with exiting the environment. 
     
     
         16 . The method of  claim 15 , further comprising:
 selecting the at least one target path to compare with the identified path based on the access point depicted in the plurality of image frames.   
     
     
         17 . The method of  claim 12 , further comprising:
 wherein updating the occupancy count of the environment is further in response to determining that the difference between the identified path and the at least one target path does not exceed the threshold difference.   
     
     
         18 . The method of  claim 12 , further comprising:
 not updating the occupancy count of the environment in response to determining that the dwell time is greater than the target dwell time.   
     
     
         19 . The method of  claim 12 , wherein the path is a combination of vectors. 
     
     
         20 . The method of  claim 12 , wherein the plurality of image frames are received in real-time from the camera as a live video feed. 
     
     
         21 . The method of  claim 12 , further comprising:
 updating a user interface on a display to present the updated value of the occupancy count.   
     
     
         22 . The method of  claim 12 , further comprising:
 generating an alert in response to determining that the updated value of the occupancy count is greater than a threshold occupancy count; and   outputting the alert on a computing device.   
     
     
         23 . A non-transitory computer-readable medium storing instructions, for use by a vision system tracking occupancy count in an environment based on detected movements, executable by a processor to:
 detect a person in a plurality of image frames captured by a camera, wherein the plurality of image frames depict an access point providing egress and ingress to the environment;   track a movement of the person in the plurality of image frames;   determine that the person has crossed a boundary within the plurality of image frames;   identify a path of the person based on the tracked movement;   compare the identified path with at least one target path associated with entering or exiting the environment;   calculate a dwell time indicative of an amount of time that the person remains within the plurality of image frames, in response to determining, based on comparing, that a difference between the identified path and the at least one target path exceeds a threshold difference;   compare the dwell time to a target dwell time;   update an occupancy count of the environment in response to determining that the dwell time is less than the target dwell time; and   store, in a memory, an updated value for the occupancy count.